landing-page-design
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to install the
belt-sh/cliand additional skills from theinference-shorganization usingnpx skills add. It also references an installation script located athttps://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.mdfor the CLI tool. - [INDIRECT_PROMPT_INJECTION]: The skill incorporates tools like
tavily/search-assistantandexa/answerthat retrieve data from external web sources. This creates a surface where the agent could potentially ingest and act upon malicious instructions hidden within web content. - Ingestion points: Search result data fetched via
belt app runcommands inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided snippets.
- Capability inventory: The skill is authorized to use the
beltCLI tool for Bash execution, AI model invocation, and web searches. - Sanitization: There is no evidence of filtering or validation for the content returned by the search tools.
Audit Metadata